I'm a Machine Learning Engineer who bridges the gap between research and production. My edge is building ML systems that actually scale—from a multimodal video dubbing platform serving 100+ concurrent users to real-time computer vision for Coca-Cola's bottling lines requiring 100% accuracy. I specialize in the unsexy but critical work: GPU-aware scheduling, VRAM optimization, and distributed architectures that don't fall over at 2 AM. I'm looking for roles where I can architect production ML systems end-to-end, particularly in multimodal AI, agentic workflows, or applied computer vision.